Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Streamlining the Development of Active Learning Methods in Real-World Object Detection
Moussa Kassem Sbeyti, Nadja Klein, Michelle Karg +2
Active learning (AL) for real-world object detection faces computational and reliability challenges that limit practical deployment. Developing new AL methods requires training mul…
cs.CV2024
Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
Fabian Diet, Moussa Kassem Sbeyti, Michelle Karg
Natural distribution shift causes a deterioration in the perception performance of convolutional neural networks (CNNs). This comprehensive analysis for real-world traffic data add…
cs.CV2024
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth +2
Object detectors in real-world applications often fail to detect objects due to varying factors such as weather conditions and noisy input. Therefore, a process that mitigates fals…